Adaptive learning under expected and unexpected uncertainty

Expected and Unexpected Uncertainty: ACh and NE in the Neocortex

Inference and adaptation in noisy and changing, rich sensory environments are rife with a variety of specific sorts of variability. Experimental and theoretical studies suggest that these different forms of variability play different behavioral, neural and computational roles, and may be reported by different (notably neuromodulatory) systems. Here, we refine our previous theory of acetylcholin...

Expected Utility Theory under Non - Classical Uncertainty ∗

In this paper Savage’s theory of decision-making under uncertainty is extended from a classical environment into a non-classical one. The Boolean lattice of events is replaced by an arbitrary ortho-complemented poset. We formulate the corresponding axioms and provide representation theorems for qualitative measures and expected utility. Then, we discuss the issue of beliefs updating and investi...

Intertemporal Decisions under Uncertainty — Com- bining Expected Utility and MaxiMin

This paper analyzes decisions on emissions of a stock pollutant under uncertainty in a two period model. Decisions are based on a weighted average of expected utility (EU) and the MaxiMin criterion. I first show that increased uncertainty aversion (less weight on EU) may lead to decreased abatement effort. The effect of learning possibilities on emissions is not clear in general, but depends qu...

Planning and Learning under Uncertainty

Robust Adaptive Routing Under Uncertainty

We consider the problem of finding an optimal history-dependent routing strategy on a directed graph weighted by stochastic arc costs when the decision maker is constrained by a travel-time budget and the objective is to optimize the expected value of a function of the budget overrun. Leveraging recent results related to the problem of maximizing the probability of termination within budget, we...